Not many people know this about me, but my wife and I met online when she was 18, and I was 20.
It wasn’t a dating website/app like Match, eHarmony, Tinder, etc.
… instead, it was Last.fm, a website that has nothing to do with dating.
Instead, Last.fm is a music website that analyzes what you listen to on your laptop, desktop, and iPod and then provides recommendations on what other music you would like.
Last.fm computed a “match score” between your music tastes and other users on the site to encourage social interactions between users.
The general idea is that you could find users with similar music preferences, discuss bands and songs together, and even meet up to go to shows and concerts.
I was a paid user of Last.fm, and one of the benefits of the pro account was that you got to see what other users were viewing your profile.
One evening I was going through my Last.fm account and noticed that a really cute girl had viewed my profile.
So, naturally, I clicked through to her profile to see what music she was interested in.
To my surprise, we had a 100% match in our music tastes.
In my 5+ years of using Last.fm, I had never seen a 100% match before.
I commented on her profile, and we started chatting.
Those conversations moved to DMs on Last.fm’s site.
Then to Facebook.
And eventually to text message/phone.
Trisha and I have now been together for 13 years and married for just over 3 years.
The crazy thing is that at the time, I was living in Maryland, and Trisha was living in New York.
It’s improbable that we would have found each other by simply going to concerts. There wouldn’t have been much geographic overlap in shows, and even if there were, there’s no guarantee we would have magically bumped into each other in a venue with 500+ people.
But … due to this obscure music website, we found each other.
In a dating world increasingly based on “swiping left/right,” I find it so amazing when I hear that technology not intended for dating ends up being used for two people to find love.
And now, PyImageSearch gets to join that club.
In this blog post, I sat down with Adithya Gaurav Singh, MSc student at the University of Maryland, College Park, who used computer vision and face recognition to help impress the girl he was interested in — and now they’ve been together for over 3 years.
I love this story because it’s so sweet and genuine.
Join me to hear Adithya’s story and how he found love using computer vision and the PyImageSearch blog.
Looking for the source code to this post?
Jump Right To The Downloads SectionAn interview with Adithya Gaurav Singh: Finding love with computer vision and face recognition
Adrian: Hi Adithya! Thank you for taking the time to do this interview. It’s a pleasure to have you on the PyImageSearch blog.
Adithya: Thank you so much, Adrian. I have been reading your blogs for quite some time. They have been a lifesaver on many, many occasions at work and in my studies.
Adrian: Before we get started, can you tell us a bit about yourself? Where do you work, and what do you do?
Adithya: I am from a small town in Northern India. Technology and designing intelligent systems have fascinated me for a long time. I completed my Bachelor’s degree in Engineering in 2018 and straight up went into the Computer Vision industry after graduation. I started small with an internship in a New Delhi-based startup, BaseApp Systems, during which I gained most of my skills in Deep Learning and its intersection with Computer Vision.
After that, I got an opportunity to work at another startup based out of Bangalore, Flux Auto. I was hired as a Deep Learning Engineer to develop the perception stack for the company’s flagship product, Flux Autonomous Driving System. After working for 2 years on a problem as challenging as autonomous driving got me intensely captivated about further exploring Computer Vision and the leverage it provides to develop really intelligent systems.
My desire to deep dive into this field has led me to the University of Maryland, College Park, MD, where I am currently pursuing a Master’s degree in Robotics. It’s been a little over a month since I reached the US, and it has been an overwhelming and pleasantly challenging experience till now.
Adrian: What got you interested in studying computer vision? I hear it was because of a girl, right?
Adithya: Like almost every Computer Vision practitioner, I started with Image Processing and was instantly amazed by the things it could do just by studying the pixels of an image. This was back in my sophomore year in undergrad school. By the time I graduated, I could already implement visual tracking systems using Computer Vision.
After graduation, I could secure an internship thanks to my very modest skills in the field. It was after starting this internship I met my now girlfriend, Ananya. We met online just like you and Trisha. Although we connected instantly on many intense topics, it wasn’t easy for me to ask her out as I’m quite shy. That’s where you came in and saved me, Adrian.
On a pretty ordinary day at work, I came across your tutorial on Face Recognition using OpenCV. You had prepared that tutorial as a special gift to Trisha, and it was a face recognition application developed to detect both of you. I found it quite endearing, and that’s when it struck me to cook up a similar application to specifically detect Ananya and give it to her as a gift.
Your tutorial and very intuitive instructions made it all the easier to code it up. I asked for 8-10 images of her, generated a 128D embedding vector for each image, and trained a small model to easily recognize the embedding vector of her face apart from anybody else. Voila, I had a functional application that could recognize her face in unseen images and videos. She was deeply touched, and it is one of the reasons we got together.
Adrian: How long have you and Ananya been dating?
Adithya: We have been dating for 3 years now, and we are very happy together.
Adrian: What was the hardest part of the project: working with the code or getting the courage to ask her out?
Adithya: Well, Adrian, while working with the code, I had your help and guidance, but with getting up to ask her out, I was pretty much on my own. Jokes apart, I can very confidently say that an OpenCV-Numpy-PyTorch based python script never made me as nervous as asking her out.
Adrian: Since you “got the girl,” is your mission in computer vision/deep learning complete? Or are you going to continue studying the field?
Adithya: Oh, I am not done with it in the slightest. Computer Vision is where I aspire to build a long-term career. I truly believe Computer Vision is the field that will play a pioneering role in achieving truly advanced Artificial Intelligence. After all, where would humans themselves be without the sense of Computer Vision?
In the last 4-5 years, I have come a fair distance. However, there’s still so far and so deep to go. Right now, my focus is to strongly perform in my graduate studies program at UMD and then get back to the industry and give my contribution in solving a plethora of problems that our Computer Vision community faces.
Adrian: What advice would you give to someone in your shoes who wants to learn computer vision and build self-confidence to succeed in their everyday lives?
Adithya: Self-confidence, in my opinion, has only one key, knowledge. The more one knows about as many things as possible, the more confident that person is. I don’t believe it has anything to do with how introverted or extroverted one is. I have personally met so many introverted people who have so much confidence in themselves but love their own company more than anyone else.
Of course, this doesn’t just include Computer Vision or any other field of specialization one pursues. It can be about anything, history, astronomy, music, food, movies, sports, and you name it. The more one knows about things, the higher the confidence goes. That’s my take.
Adrian: Thank you for being a member of PyImageSearch University! Would you recommend the program to other readers who want to learn computer vision, deep learning, and OpenCV?
Adithya: I wholeheartedly recommend PyImageSearch University, no matter your skill level in Computer Vision/Deep Learning. Even as an experienced practitioner, many people tend to get rusty with the field’s fundamental ABCs.
This program covers you by bridging this gap and helps in selecting the right tool to solve a given problem. For beginners, I’d say it won’t be easy to find a degree program that teaches Computer Vision from basic to advanced as affordably as 24 USD per month. PyImageSearch University is the go-to avenue for gaining skills in Computer Vision and Deep Learning.
Adrian: If a PyImageSearch reader wants to connect with you, how can they do so?
Adithya: I will be delighted to connect to any PyImageSearch reader through my LinkedIn profile or via email agsingh [at] terpmail [dot] umd [dot] edu
Summary
Today we interviewed Adithya Gaurav Singh, MSc student at the University of Maryland, College Park.
Adithya used computer vision and the face recognition tutorials on the PyImageSearch blog to impress the girl he was interested in.
They’ve now been dating for 3 years.
It just shows you that with a bit of creativity, you don’t need to swipe left/right.
Technology, and even face recognition tutorials with OpenCV and Python, can be used organically to foster a relationship … and I think that is a beautiful thing.
To be notified when future tutorials and interviews are published here on PyImageSearch, enter your email address in the form below!
Join the PyImageSearch Newsletter and Grab My FREE 17-page Resource Guide PDF
Enter your email address below to join the PyImageSearch Newsletter and download my FREE 17-page Resource Guide PDF on Computer Vision, OpenCV, and Deep Learning.
Comment section
Hey, Adrian Rosebrock here, author and creator of PyImageSearch. While I love hearing from readers, a couple years ago I made the tough decision to no longer offer 1:1 help over blog post comments.
At the time I was receiving 200+ emails per day and another 100+ blog post comments. I simply did not have the time to moderate and respond to them all, and the sheer volume of requests was taking a toll on me.
Instead, my goal is to do the most good for the computer vision, deep learning, and OpenCV community at large by focusing my time on authoring high-quality blog posts, tutorials, and books/courses.
If you need help learning computer vision and deep learning, I suggest you refer to my full catalog of books and courses — they have helped tens of thousands of developers, students, and researchers just like yourself learn Computer Vision, Deep Learning, and OpenCV.
Click here to browse my full catalog.